Provider

RRadixark

Every Radixark model UltraGPT can reach, kept in sync with the live catalog — pricing, context window and capabilities for each one.

1 model from Radixark Up to 262.1K tokens of context
Open the appBrowse every provider

1

Models tracked

1

Providers

1

Reasoning models

1

See images (vision)

262K

Largest context window

0

Free to run

Directory

All Radixark models.

Search and filter this provider's lineup — pricing per million tokens, context window, modalities, reasoning effort and independent benchmark scores where available.

1 of 1 models

DaisyRose 27B is an open-weight multimodal reasoning model from RadixArk, trained from Qwen3.8 27B using reinforcement learning only on long-horizon agent tasks, with no supervised fine-tuning or distillation. It is...

ReasoningTool callingVisionStreamingJSON mode
Context window262.1K tok
Max output235.9K tok
ReleasedNov 21, 2026
Knowledge cutoff—
Text + ImageText
Input$0.15 / 1M tok
Output$1.88 / 1M tok
Cache read$0.037 / 1M tok
Effort: xhigh, medium, low, none

Every Radixark model above, one subscription away.

UltraGPT puts this whole directory behind a single login and one flat monthly price — no separate bill per provider.